polymer informatics
4 articles · search the full text for this term
-
Generative AI for Designing Sustainable Polymer Composites for Renewable Energy Applications
Abstract: Sustainable polymer composites are increasingly required for renewable energy devices, yet conventional trial-and-error formulation cannot efficiently balance performance, processability, recyclability, and environmental constraints. This study proposes a generative artificial intelligence framework for designing polymer composites for photovoltaic encapsulation, dielectric energy storage, polymer electrolytes, and thermal-management systems. Public polymer-property and composite datasets were curated from open databases and published supplementary records. Chemical descriptors, molecular fingerprints, polymer embeddings, processing variables, and sustainability …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 Read article
-
Machine Learning-Based Quantification of Polymer Structure Property Relationships for Predictive Material Design
Abstract: Polymer structures exhibit complex, hierarchical arrangements that strongly influence macroscopic properties, yet consistent quantification remains challenging due to nonlinear interactions and limited unified modeling strategies. Existing approaches inadequately capture generalized structure–property mappings across diverse polymer systems. This research aims to establish a machine learning-based quantification model for polymer structure–property relationships to support predictive material design. A Polymer Structure Property Dataset of 5,000 polymer samples includes structural descriptors and experimentally measured …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 737–754 Read article
-
Structure Property Correlation of Polymer Dielectrics Using Electrical Response Data
Abstract: Polymer dielectrics are foundational to insulation, capacitors, embedded passives, and flexible electronics, where performance is governed by the frequency-dependent electrical response rather than a single dielectric constant. This study presents a spectroscopy-aware structure–property correlation framework that transforms dielectric response data into physically interpretable spectral fingerprints and learns mappings from polymer descriptors to these fingerprints for prediction and interpretation. Broadband spectra are standardized on a log-frequency grid and parameterized using relaxation-informed …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 315–324 Read article
-
Predicting Dielectric Constants of Polymers Using Molecular Structural Descriptors and Explainable Machine Learning: A Data-Driven Approach
Abstract: Accurate prediction of dielectric constants in polymeric materials is fundamental to the rational design of advanced electronic components, energy storage capacitors, flexible substrates, and high-frequency communication circuits. Conventional approaches to identifying suitable polymer dielectrics rely on extensive experimental synthesis and characterisation, which are both time-consuming and resource-intensive. In this work, an explainable machine learning framework is developed to predict the dielectric constant of polymers directly from molecular structural descriptors derived …
Published in Journal of Polymer & Composites · Vol. 14, Issue 3, 2026 · pp. 297–304 Read article